How to Use the Carbonara MCP in CrewAI

Q: How do I restrict Carbonara access in CrewAI?

Use the toolfilter option in your MCP configuration. This prevents unauthorized agents from calling the image tool.

Use the Carbonara MCP server to give your CrewAI agents the ability to generate beautiful code images.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Carbonara MCP to CrewAI

Create your Vinkius account to connect Carbonara to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Carbonara with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Visualizing outputs with CrewAI

Assign the `cook_code_image` tool to a specialized agent in your crew. When the research agent finds a code block, the visual agent converts it into a clean PNG. This division of labor keeps your agents focused. One agent gathers the logic, and the other produces the visual artifact.

Collaborative image creation

Your agents share memory regarding the code to be rendered. By calling `cook_code_image`, they produce assets that other agents can then attach to final reports. It makes your automated operations look professional. You get high-quality images without needing a design background.

Scaling documentation with MCP

Deploy this MCP server across multiple agent crews to generate documentation at scale. Each agent uses the same `cook_code_image` tool to ensure consistent branding across your team's output. It simplifies your setup. You don't need to maintain local scripts for image formatting.

Setup guide

Set up Carbonara MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Carbonara tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Carbonara Analyst",
    goal="Access and analyze Carbonara data via MCP.",
    backstory="Expert analyst with direct Carbonara access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Carbonara transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Carbonara Analyst",
        goal="Access and analyze Carbonara data via MCP.",
        backstory="Expert analyst with direct Carbonara access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Carbonara transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Carbonara. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Carbonara now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Carbonara MCP in CrewAI

Yes, just pass the server URL to your agent definition. Every member of the crew can then use the rendering tool.

The tool is available to any agent you authorize. Hierarchical setups can pass the code data down to the agent responsible for rendering.

Use the tool_filter option in your MCP configuration. This prevents unauthorized agents from calling the image tool.

They are rendered for clarity and readability. You get a crisp PNG that displays well on any screen.

We enforce strict isolation for every request. The code you send to the server is never logged and is scrubbed immediately after the PNG is returned.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript

Mastra AI sdk-typescript

Start using the Carbonara MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started